A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Nothing to run from here
Derive is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
87/100
trust score
3
downloads a day
local
runs on your machine
65
downloads in 30d
What it does
Derive — MCP server and CLI for autonomous systems engineering. 27 tools: project overview, requirements CRUD, trace links, quality gates, ISO 15289 reports, SysML v2 export, hazard registers, knowledge graph, diagrams, baselines, and verification matrix.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user derive-mcp '--' npx -y derive-mcp
# 2 — ask your agent for something these tools do
# list_diagrams, render_diagram, get_harness_state and 23 more
Derive costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ASAll 1 server
airgen-studio1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Derive as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user derive-mcp '--' npx -y derive-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
26 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List all architecture diagrams for a project with IDs, names, and views
No parameter schema on file.
Render an architecture diagram as Mermaid syntax
No parameter schema on file.
Get current harness operational state: active project, flow state, session count, last session info, live session status, loop status
No parameter schema on file.
Get the state machine definition: states with labels, transitions with guards, flows, and priorities
No parameter schema on file.
List recent autonomous session journal entries with date, title, session number, task class, and excerpt
No parameter schema on file.
Get the full markdown content of a journal entry
No parameter schema on file.
List classified entities in a project
No parameter schema on file.
Query the knowledge graph. Predicates: PART_OF, CONNECTS, PRODUCES, HAS_STAKEHOLDER, HAS_CONSTRAINT, INTERFACES_WITH, HAS_HAZARD, HAS_MISSION, HAS_MODE, HAS_SCENARIO, SPEC_TREE, RED_TEAM_FINDING
No parameter schema on file.
Get the hazard register with linked requirements for each hazard. Shows which requirements mitigate each hazard based on SIL tags and rationale references.
No parameter schema on file.
List all systems engineering projects with slug, name, requirement count, and status
No parameter schema on file.
Compare all SE projects: requirement counts, trace coverage, orphan counts, and quality gate status across the entire portfolio. Use this to find the best/worst projects or identify patterns.
No parameter schema on file.
Get project summary: requirement counts by document type, decomposition tree, subsystems, standards, diagrams with IDs, quality gate status. Does NOT return full requirement text.
No parameter schema on file.
Comprehensive single-call project review: overview + quality gates + all high-severity lint findings + orphan requirements with document type + hazard register + diagrams + recent journal entries. Best starting point for reviewing a project.
No parameter schema on file.
Import a local document (PDF, DOCX, MD, TXT) into a project. Extracts text, runs Claude to identify requirements/stakeholders/hazards, and stores as Substrate facts for the concept flow to consume. Creates the project if it doesn
No parameter schema on file.
Run semantic requirements lint. Returns findings with severity, affected requirement ref, finding type, and description. Supports filtering by severity and document type.
No parameter schema on file.
Evaluate quality gates (isFirstPassComplete, isQCPassed, isValidated) for a specific project. Shows each metric vs its threshold.
No parameter schema on file.
Generate SysML v2 textual notation (.sysml) for a Derive project. Maps requirements, trace links, PART_OF hierarchy, connections, modes, hazards, and constraints to valid SysML v2 constructs. Returns the full .sysml text and line/construct counts.
No parameter schema on file.
Get paginated requirements for a project, optionally filtered by document type (stakeholder-requirements, system-requirements, subsystem-requirements, interface-requirements, architecture-decisions, verification-requirements)
No parameter schema on file.
Get full detail of a single requirement including all trace links to/from it
No parameter schema on file.
Full-text search across requirement text and rationale. Returns up to 30 matches.
No parameter schema on file.
Get trace link summary and first 100 links. Shows coverage statistics and structural gaps (groups of requirements missing derivation/verification links).
No parameter schema on file.
Find requirements with no trace links. Includes document type for severity assessment (STK orphans are critical, SUB orphans less so).
No parameter schema on file.
Compare two baselines to see what changed between them — added, removed, and modified requirements. Uses airgen diff (v0.21.0+).
No parameter schema on file.
List all baselines (snapshots) for a project with refs and dates.
No parameter schema on file.
Get the verification cross-reference matrix — shows which requirements are verified, by what method, and coverage gaps.
No parameter schema on file.
Get project activity timeline — recent changes to requirements, trace links, and baselines.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Derive or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
BTrust score 87 / 100
Release 0.3.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score94
Client score87
Findings3 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digeste8a67b964c7f5fda47223448260c38bea03213f32364e087f3dcd5687f5b35f1
Score vectorthreat 94 → client 87
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can execute shell commands or code
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digeste8a67b964c7f5fda
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.3.0. Pin a release below and the command asks for exactly that one.
0.3.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Derive can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.